Fault Diagnosis Design Method and System Based on Commissioning and Testing Experience

Abstract

This invention discloses a fault diagnosis design method and system based on commissioning and testing experience knowledge, belonging to the field of integrated aviation equipment commissioning and testing. The method includes the following steps: S1, preprocessing commissioning and testing fault data; S2, constructing a diagnostic knowledge model; S3, designing a similarity matching algorithm to match the target fault phenomenon with the fault experience knowledge base; and S4, improving the fault knowledge base. This invention improves the efficiency of commissioning and testing fault diagnosis for integrated aviation equipment, changing the existing model that relies on technical personnel for commissioning and testing fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of integrated aviation equipment commissioning and testing, and more specifically, to a fault diagnosis design method and system based on commissioning and testing experience. Background Technology

[0002] Currently, the commissioning and fault diagnosis of integrated aviation equipment mainly relies on technical personnel. Due to the high degree of integration of integrated aviation equipment, there are significant gaps in commissioning and testing technologies between different models and projects, and the training cycle for technical personnel is too long. Therefore, relying on technical personnel for fault diagnosis is far from meeting the production needs of integrated equipment, and the efficiency of commissioning and fault diagnosis of integrated aviation equipment is low. People in this field urgently need to change the current model of relying on technical personnel for commissioning and fault diagnosis. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a fault diagnosis design method and system based on commissioning and testing experience, which improves the efficiency of commissioning and testing fault diagnosis of integrated aviation equipment and changes the existing mode of relying on technicians for commissioning and testing fault diagnosis.

[0004] The objective of this invention is achieved through the following solution:

[0005] A fault diagnosis design method based on debugging experience includes the following steps:

[0006] S1, Preprocessing of fault data during commissioning;

[0007] S2, Construct a diagnostic knowledge model;

[0008] S3, Design a similarity matching algorithm to match the target fault phenomenon with the fault experience knowledge base;

[0009] S4, with a comprehensive fault knowledge base.

[0010] Furthermore, in step S1, the preprocessing of the debugging fault data specifically includes: debugging fault attribute analysis, debugging fault element extraction, and debugging fault data transformation.

[0011] The aforementioned fault attribute analysis, through the analysis of the debugging process of integrated aviation equipment, and based on empirical fault data, classifies the product attributes, environmental attributes, and logical attributes of equipment debugging faults, forming attribute classes.

[0012] The extraction of debugging and testing fault elements involves analyzing existing experience fault data of integrated aviation equipment and combining it with the unique attributes of debugging and testing faults to form a debugging and testing fault element table.

[0013] The debugging and testing fault data transformation involves transforming existing debugging and testing fault data according to the debugging and testing fault element table to form a standardized debugging and testing fault experience database.

[0014] Furthermore, in step S2, the construction of the diagnostic knowledge model specifically includes: functional knowledge structure analysis and functional fault mapping analysis;

[0015] The functional knowledge structure analysis, through the design principles of integrated aviation equipment, sorts out the equipment's functional sets, integrated sub-units, and configuration modules to form a standardized functional knowledge structure tree.

[0016] The functional fault mapping analysis is based on existing commissioning and testing fault experience data, and establishes the logical relationship between equipment functional technical indicators, fault root causes and fault phenomena.

[0017] Further, in step S3, the design of the similarity matching algorithm includes the following sub-steps:

[0018] S31, based on the analyzed equipment function knowledge structure tree, establish function sets, integrated sub-unit sets, and configuration module sets, and set:

[0019] The set of functions F = {f1, f2, f3, ..., f n1};

[0020] Integrated extension set I = {i1,i2,i3,…,i n2};

[0021] The configuration module set M = {m1, m2, m3, ..., m} n3};

[0022] Among them, f n1 For a specific function implemented by integrated aviation equipment, n1 is the number of functions, i n2 An integrated sub-unit for realizing a certain function in integrated aviation equipment, where n2 is the number of sub-units, and m n3 The configuration modules required to realize a certain function of integrated aviation equipment, where n3 is the number of modules;

[0023] S32, based on the analyzed equipment functional fault mapping, establish a set of functional technical indicators and set:

[0024] Technical indicator set T = {t1, t2, t3, ..., t n4};

[0025] Among them, t n4 n4 represents a specific functional technical indicator for integrated aviation equipment, where n4 is the number of functional technical indicators.

[0026] S33, for the target fault phenomenon description and a standard fault phenomenon description in the debugging fault knowledge base, the text values ​​are segmented using a Chinese word segmentation algorithm of natural language processing to obtain two fault phenomenon word sets, set as follows:

[0027] Target Fault Phenomenon Terminology

[0028] Standard Fault Phenomenon Terminology

[0029] in, The target fault phenomenon is described by word segmentation, where n5 is the number of words to be segmented. The description of a standard fault phenomenon is segmented into words, where n6 is the number of words to be segmented.

[0030] S34, Settings:

[0031] C1=F∩W T ct1 is the number of elements in set C1;

[0032] C2=I∩W T ct2 is the number of elements in set C2;

[0033] C3=M∩W T ct3 is the number of elements in set C3;

[0034] C4=T∩W T ct4 represents the number of elements in set C4;

[0035] C5 = W S ∩W T ct5 represents the number of elements in set C5;

[0036] S35, based on the different degrees of influence of integrated fault attributes, functional attributes, integrated sub-units, configuration modules, and technical indicators on fault diagnosis, weights are assigned to them as P1, P2, P3, and P4 respectively. The similarity of the target fault is then calculated as follows:

[0037]

[0038] S36, For the standard fault records in the debugging fault knowledge base, repeat steps S33 to S35 to obtain a set of target fault similarities. Where e i To test the number of standard fault records in the fault knowledge base, the standard fault record corresponding to the maximum value in the similarity array is the matching output result.

[0039] Furthermore, in step S4, the fault knowledge base is improved. Specifically, in cases where the similarity matching algorithm fails to find a match or the matched standard fault knowledge cannot resolve the target fault, the technical personnel resolve the target fault, and at the same time, fault knowledge data is recorded according to the fault attributes and fault elements.

[0040] Furthermore, the product attributes are equipment component entities, including equipment functions, sub-units, and modules;

[0041] The environmental attributes refer to the environmental conditions when the fault occurs, including normal temperature, high temperature, low temperature, low pressure, and vibration.

[0042] The logical attributes represent the root causes and solutions for debugging failures. The root causes include component, software, and process factors, representing the causal relationship that leads to the failure phenomenon.

[0043] Furthermore, the logical relationships between the aforementioned fault phenomena include belonging relationships, causing relationships, and associative relationships;

[0044] The relationship described is that the fault phenomenon belongs to a certain product attribute of the equipment;

[0045] The aforementioned relationship is that a failure of a certain component of the equipment leads to a failure of a certain attribute of the product, or a failure of a certain attribute of the product leads to a failure of another product attribute, which exists in the equipment function implementation process.

[0046] The correlation is the relationship between the product failure phenomenon and the failure environment attributes of the debugging system.

[0047] A fault diagnosis system based on debugging experience includes:

[0048] The preprocessing module is used for preprocessing test fault data;

[0049] The diagnostic knowledge model building module is used to build diagnostic knowledge models;

[0050] The similarity matching module is used to design similarity matching algorithms to match target fault phenomena with the fault experience knowledge base.

[0051] The Fault Knowledge Base Improvement Module is used to improve the fault knowledge base.

[0052] Furthermore, the diagnostic knowledge model construction module includes a functional knowledge structure analysis module and a functional fault mapping analysis module;

[0053] The functional knowledge structure analysis module is used to sort out the set of equipment working functions, integrated sub-units, and configuration modules through the design principles of integrated aviation equipment, and form a standardized functional knowledge structure tree.

[0054] The functional fault mapping analysis module is used to establish the logical relationship between equipment functional technical indicators, fault root causes and fault phenomena based on existing commissioning and testing fault experience data.

[0055] Furthermore, the similarity matching module includes:

[0056] The first settings module is used to establish a set of functions, a set of integrated sub-units, and a set of configuration modules based on the sorted equipment function knowledge structure tree. Settings include:

[0057] The set of functions F = {f1, f2, f3, ..., f n1};

[0058] Integrated extension set I = {i1,i2,i3,…,i n2};

[0059] The configuration module set M = {m1, m2, m3, ..., m} n3};

[0060] Among them, f n1 For a specific function implemented by integrated aviation equipment, n1 is the number of functions, i n2 An integrated sub-unit for realizing a certain function in integrated aviation equipment, where n2 is the number of sub-units, and m n3 The configuration modules required to realize a certain function of integrated aviation equipment, where n3 is the number of modules;

[0061] The second setting module is used to establish a set of functional technical indicators based on the analyzed equipment functional fault mapping. The settings include:

[0062] Technical indicator set T = {t1, t2, t3, ..., t n4};

[0063] Among them, t n4 n4 represents a specific functional technical indicator for integrated aviation equipment, where n4 is the number of functional technical indicators.

[0064] The third setting module is used to segment the text values ​​of the target fault phenomenon description and a standard fault phenomenon description from the debugging fault knowledge base using a Chinese word segmentation algorithm based on natural language processing, resulting in two fault phenomenon word sets. The settings are as follows:

[0065] Target Fault Phenomenon Terminology

[0066] Standard Fault Phenomenon Terminology

[0067] in, The target fault phenomenon is described by word segmentation, where n5 is the number of words to be segmented. The description of a standard fault phenomenon is segmented into words, where n6 is the number of words to be segmented.

[0068] The fourth settings module is used to configure:

[0069] C1=F∩W T ct1 is the number of elements in set C1;

[0070] C2=I∩W T ct2 is the number of elements in set C2;

[0071] C3=M∩W T ct3 is the number of elements in set C3;

[0072] C4=T∩W T ct4 represents the number of elements in set C4;

[0073] C5 = W S ∩W T ct5 represents the number of elements in set C5;

[0074] The target fault similarity calculation module is used to assign weights P1, P2, P3, and P4 to the comprehensive fault attributes, functional attributes, integrated sub-units, configuration modules, and technical indicators based on their varying degrees of influence on fault diagnosis. The target fault similarity is then calculated as follows:

[0075]

[0076] The maximum value lookup module is used to repeat the process from the third setting module to the target fault similarity calculation module for standard fault records in the debugging fault knowledge base, to obtain a set of target fault similarities. Where e i To test the number of standard fault records in the fault knowledge base, the standard fault record corresponding to the maximum value in the similarity array is the matching output result.

[0077] The beneficial effects of this invention include:

[0078] (1) Experience data on the commissioning and testing of integrated aviation equipment has enabled knowledge storage and inheritance. This invention makes full use of the discrete fault record data of current integrated aviation equipment by establishing a commissioning and testing fault knowledge base, thereby realizing the accumulation and storage of commissioning and testing fault knowledge. At the same time, it provides a method and approach for the inheritance of commissioning and testing fault knowledge in the form of a knowledge base.

[0079] (2) The demand for technical personnel for troubleshooting and diagnosing integrated aviation equipment is reduced. This invention achieves automatic analysis and location of troubleshooting faults through fault diagnosis design based on troubleshooting experience and knowledge, breaking the current model of assigning technical personnel to different models and projects for fault diagnosis, and reducing the cost of technical personnel.

[0080] (3) The fault diagnosis design method based on commissioning and testing experience is easy to promote and apply. The design method adopted in this invention is applicable to the commissioning and testing process of integrated aviation equipment. Due to the high degree of integration and complexity of current integrated aviation products, a large amount of fault experience data has been accumulated during the production process, with a rich sample size of faults. At the same time, the data processing and similarity matching algorithms are uniform, applicable to different models and different projects, and have strong portability and replicability, making it easy to promote and apply. Attached Figure Description

[0081] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0082] Figure 1 This is a flowchart illustrating a fault diagnosis design method for a certain type of integrated aviation equipment based on debugging and testing experience, according to an embodiment of the present invention. Detailed Implementation

[0083] All features disclosed in all embodiments of this specification, or steps in all methods or processes implied in the disclosure, may be combined and / or extended or replaced in any way, except for mutually exclusive features and / or steps.

[0084] In view of the technical problems in the background, the inventors of this invention, after creative thinking, believe that fault diagnosis based on commissioning and testing experience knowledge can be achieved by standardizing the fault data accumulated in the commissioning and testing process of integrated aviation equipment, extracting fault elements to form structured and standardized experience knowledge, establishing a diagnostic knowledge model, and realizing automatic analysis and location of faults in the commissioning and testing process based on similarity matching algorithms.

[0085] Further conceptualization reveals that fault diagnosis design based on commissioning and testing experience mainly involves several stages: preprocessing commissioning and testing fault data, constructing a diagnostic knowledge model, designing a similarity matching algorithm, and improving the fault knowledge base.

[0086] Data preprocessing involves structuring and standardizing fault data accumulated during the commissioning and testing of integrated aviation equipment. This is mainly achieved by analyzing commissioning and testing attributes, classifying fault attributes, extracting fault elements, and transforming commissioning and testing experience fault data.

[0087] The process of building a diagnostic knowledge model involves converting loosely described diagnostic information stored in databases or tabular files into a standardized, structured diagnostic knowledge graph model based on the functional principles of integrated aviation equipment and the mapping relationship between fault elements and functional knowledge structures.

[0088] The design of the similarity matching algorithm is aimed at the matching calculation process of the target fault attributes with the standard record attributes in the commissioning fault knowledge base. The algorithm performs word segmentation processing on the target fault text language, and applies constraints such as functional attributes, integrated sub-units, configuration modules, and functional technical indicators. Then, it matches the target fault with the standard fault phenomenon records one by one. Based on the similarity matching results, the similarity between the target fault and the standard record faults in the commissioning fault knowledge base is calculated, thereby achieving the fault matching purpose.

[0089] The fault knowledge base improvement process involves entering fault information through the fault knowledge base maintenance function for information that is not matched with applicable knowledge data in the fault knowledge base or whose matched knowledge data fails to resolve the target fault.

[0090] In a further embodiment, this example provides a fault diagnosis design method based on debugging experience, including the following steps:

[0091] S1, Preprocessing of fault data during commissioning;

[0092] S2, Construct a diagnostic knowledge model;

[0093] S3, Design a similarity matching algorithm;

[0094] S4, with a comprehensive fault knowledge base;

[0095] By completing the above stages, a fault diagnosis design method based on debugging experience and knowledge can be realized.

[0096] In a further embodiment, the fault data preprocessing includes the following sub-steps:

[0097] The relevant content includes fault attribute analysis, fault element extraction, and fault data transformation. Fault attribute analysis refers to classifying faults based on experience fault data by analyzing the debugging process of integrated aviation equipment, categorizing them into product attributes, environmental attributes, and logical attributes to form attribute classes. Product attributes refer to the physical components of the equipment, mainly including equipment functions, sub-units, and modules; environmental attributes refer to the environmental conditions at the time of the fault, mainly including normal temperature, high temperature, low temperature, low pressure, and vibration; logical attributes are the root causes and solutions to the faults. Root causes include factors such as components, software, and processes, representing the causal relationship leading to the fault phenomenon. Fault element extraction involves analyzing existing experience fault data of integrated aviation equipment and combining it with the unique attributes of faults to form a fault element table. Fault data transformation refers to transforming existing fault data according to the fault element table to form a standardized fault experience database.

[0098] In a further implementation, the construction of the diagnostic knowledge model includes the following sub-steps:

[0099] The relevant content includes functional knowledge structure analysis and functional fault mapping analysis. Functional knowledge structure analysis primarily utilizes the design principles of integrated aviation equipment to organize the equipment's functional sets, integrated subsystems, and configuration modules, forming a standardized functional knowledge structure tree. Functional fault mapping analysis mainly establishes the logical relationships between equipment functional technical indicators, fault root causes, and fault phenomena based on existing debugging and testing fault experience data. These relationships include attribution, causal, and correlation relationships. Attribution relationships refer to the fault phenomenon belonging to a specific product attribute of the equipment; for example, poor voice call quality in a UV device belongs to the UV function. Causation relationships refer to a fault in a component of the equipment causing a fault in a specific product attribute, or a fault in a specific product attribute leading to a fault in another product attribute; these mainly exist in the equipment's functional implementation process. Correlation relationships refer to the correlation between the product fault phenomenon and the environmental attributes of the debugging and testing fault, such as low-temperature faults and high-temperature faults.

[0100] In a further embodiment, the design of the similarity matching algorithm includes the following sub-steps:

[0101] The main purpose of this project is to match the target fault phenomenon with the fault experience knowledge base. The steps are as follows.

[0102] Step 1: Based on the analyzed equipment function knowledge structure tree, establish function sets, integrated sub-unit sets, and configuration module sets, and set...

[0103] The set of functions F = {f1, f2, f3, ..., f n1};

[0104] Integrated extension set I = {i1,i2,i3,…,i n2};

[0105] The configuration module set M = {m1, m2, m3, ..., m} n3};

[0106] Where f n1 For a specific function implemented by integrated aviation equipment, n1 represents the number of functions; i n2 For integrated sub-units that perform a specific function in integrated aviation equipment, n2 represents the number of sub-units; m n3 The configuration modules required to realize a certain function of integrated aviation equipment, where n3 is the number of modules;

[0107] Step 2: Based on the analyzed equipment functional fault mapping, establish a set of functional technical indicators, and set the technical indicator set T = {t1, t2, t3, ..., t...} n4};

[0108] Where t n4 n4 represents a specific functional technical indicator for integrated aviation equipment, where n4 is the number of functional technical indicators.

[0109] Step 3: For the target fault phenomenon description and a standard fault phenomenon description from the debugging fault knowledge base, perform word segmentation using a Chinese word segmentation algorithm based on natural language processing to obtain two fault phenomenon word sets.

[0110] Target Fault Phenomenon Terminology

[0111] Standard Fault Phenomenon Terminology

[0112] in The target fault phenomenon is described by word segmentation, where n5 is the number of words to be segmented. The description of a standard fault phenomenon is segmented into words, where n6 is the number of words to be segmented.

[0113] Step 4, settings

[0114] C1=F∩W T ct1 is the number of elements in set C1;

[0115] C2=I∩W T ct2 is the number of elements in set C2;

[0116] C3=M∩W T ct3 is the number of elements in set C3;

[0117] C4=T∩W T ct4 represents the number of elements in set C4;

[0118] C5 = W S ∩W T ct5 represents the number of elements in set C5;

[0119] Step 5: Based on the different degrees of influence of comprehensive fault attributes, functional attributes, integrated sub-units, configuration modules, and technical indicators on fault diagnosis, assign weights of P1, P2, P3, and P4 respectively. Then, the target fault similarity is calculated.

[0120]

[0121] Step 6: For the standard fault records in the debugging fault knowledge base, repeat steps 3 to 5 to obtain a set of target fault similarity scores. Where e i To test the number of standard fault records in the fault knowledge base, the standard fault record corresponding to the maximum value in the similarity array is the matching output result.

[0122] In a further implementation, the fault knowledge base is improved, including the following sub-steps:

[0123] The relevant content mainly addresses situations where similarity matching algorithms fail to produce results or the standard fault knowledge obtained from the matching cannot resolve the target fault. It involves technical personnel resolving the target fault and recording fault knowledge data according to the fault attributes and elements being tested.

[0124] With the increasing demand for integrated aviation equipment, there are more stringent requirements for the rapid diagnosis of faults in the production and after-sales processes. The fault diagnosis design method based on debugging experience knowledge of the present invention can significantly shorten the fault diagnosis and maintenance cycle, while saving the input of manpower and material resources in the process. It is a method that achieves twice the result with half the effort.

[0125] This invention, through the implementation and application of a fault diagnosis design method based on commissioning and testing experience, improves the commissioning and production efficiency of equipment to a certain extent. The fault diagnosis design based on commissioning and testing experience utilizes fault experience data accumulated during the commissioning and testing process of integrated aviation equipment to establish a continuously accumulating and improving knowledge base of commissioning and testing faults. Based on a similarity matching algorithm, it achieves automatic analysis and matching of commissioning and testing faults within the knowledge base, thus achieving the goal of rapid fault diagnosis.

[0126] In other embodiments of the invention, such as Figure 1As shown, this embodiment of the invention first preprocesses the past debugging and testing fault experience data of a certain type of integrated aviation equipment to form a standardized debugging and testing fault database corresponding to this type of integrated aviation equipment; then, it performs functional knowledge structure analysis and functional fault mapping analysis on this type of equipment to construct a debugging and testing fault diagnosis model suitable for this type of equipment; finally, by establishing a similarity matching algorithm input set, it forms an algorithm suitable for debugging and testing fault matching of this type of equipment. As the sample size continues to increase, the debugging and testing fault diagnosis efficiency will become higher and higher.

[0127] Taking a certain type of integrated aviation equipment as an example, the following implementation steps are adopted:

[0128] Step 1: By analyzing the attributes of debugging and testing faults, classify the product attributes, environmental attributes, and logical attributes of equipment debugging and testing faults to form attribute classes, as shown in Table 1.

[0129] Table 1 Attribute Classification Table for a Certain Type of Equipment

[0130]

[0131] Based on the existing experience and fault data of this type of equipment, fault elements are identified and a fault element table is constructed, as shown in Table 2. The existing commissioning and testing fault data is then transformed according to the fault element table to form a standardized commissioning and testing fault experience database, as shown in Table 3.

[0132] Table 2 Fault Element Table

[0133]

[0134] Table 3. Fault Database for Testing and Adjustment

[0135]

[0136] Step 2: Perform functional and fault mapping modeling for this type of equipment, as shown in Table 4.

[0137] Table 4 Functional and Fault Mapping Modeling

[0138]

[0139] Step 3: Set the input set for the similarity matching algorithm corresponding to this model, and set...

[0140] Function set F = {UV function, HF function, ILS function, MLS function, TACAN function, ATC function, ...};

[0141] Integrated unit set I = {low-frequency rack, communication control box, HF power amplifier, HF antenna tuner, etc.};

[0142] The configuration module set M = {UVRT module, UV antenna interface module, UV receiver module, UV excitation module, MLSM module, HFM module, LB receiver module, LB excitation module, ...};

[0143] Technical specification set T = {UV voice receiver sensitivity, UV voice receiver distortion, UV voice receiver dynamic range, RF input frequency, gain control range...};

[0144] Step 4: Taking the target fault of this model, "Noise in UV voice reception during low-frequency rack room temperature debugging," and the standard fault record, "During room temperature debugging, on the first power-on test, the UV function is abnormal; the scanning and excitation signals of the 'transmit' channel are normal, but the 'receive' channel cannot receive; low-frequency rack; UVRT; room temperature debugging; room temperature; first power-on; UV function; reception; reception sensitivity; stable," as an example, we obtain...

[0145] Target Fault Phenomenon Terminology W T ={Low-frequency rack, room temperature debugging, UV voice, low frequency, rack, room temperature, debugging, UV, voice, reception, noise};

[0146] Standard Fault Phenomenon Terminology W S ={Room temperature debugging, first power-on, UV function, scan signal, excitation signal, low frequency rack, first power-on, room temperature, debugging, first, power-on, test, UV, function, abnormal, transmit, channel, scan, signal, excitation, normal, receive, unable, low frequency, rack, UVRT, power-on, sensitivity, stable};

[0147] Step 5: Settings

[0148] C1=F∩W T If the intersection element count is ct1, then the number of elements in the intersection is 0.

[0149] C2=I∩W T If the intersection element count is ct2, then the number of elements in the intersection is 1.

[0150] C3=M∩W T Then the number of elements in the intersection is ct3 = 1;

[0151] C4=T∩W T If the intersection element count is ct4, then the number of elements in the intersection is 0.

[0152] C5 = W S ∩W T Then the number of elements in the intersection is ct5 = 8;

[0153] Step 6: Set the influence weights of functional attributes, integrated extensions, configuration modules, and technical indicators on fault diagnosis to 1, 0.8, 0.5, and 0.3, respectively. Then, the target fault similarity...

[0154]

[0155] For the standard fault records in the debugging fault knowledge base, repeat steps 3 to 5 to obtain a set of target fault similarities. The standard fault record corresponding to the maximum similarity is the matching output result.

[0156] It should be noted that, within the scope of protection defined in the claims of this invention, the following embodiments can be combined and / or extended or replaced in any logical manner from the above specific embodiments, such as the disclosed technical principles, disclosed technical features or implicitly disclosed technical features.

[0157] Example 1

[0158] A fault diagnosis design method based on debugging experience includes the following steps:

[0159] S1, Preprocessing of fault data during commissioning;

[0160] S2, Construct a diagnostic knowledge model;

[0161] S3, Design a similarity matching algorithm to match the target fault phenomenon with the fault experience knowledge base;

[0162] S4, with a comprehensive fault knowledge base.

[0163] Example 2

[0164] Based on Example 1, in step S1, the preprocessing of the debugging fault data specifically includes: debugging fault attribute analysis, debugging fault element extraction, and debugging fault data transformation.

[0165] The aforementioned fault attribute analysis, through the analysis of the debugging process of integrated aviation equipment, and based on empirical fault data, classifies the product attributes, environmental attributes, and logical attributes of equipment debugging faults, forming attribute classes.

[0166] The extraction of debugging and testing fault elements involves analyzing existing experience fault data of integrated aviation equipment and combining it with the unique attributes of debugging and testing faults to form a debugging and testing fault element table.

[0167] The debugging and testing fault data transformation involves transforming existing debugging and testing fault data according to the debugging and testing fault element table to form a standardized debugging and testing fault experience database.

[0168] Example 3

[0169] Based on Example 1, in step S2, the construction of the diagnostic knowledge model specifically includes: functional knowledge structure analysis and functional fault mapping analysis;

[0170] The functional knowledge structure analysis, through the design principles of integrated aviation equipment, sorts out the equipment's functional sets, integrated sub-units, and configuration modules to form a standardized functional knowledge structure tree.

[0171] The functional fault mapping analysis is based on existing commissioning and testing fault experience data, and establishes the logical relationship between equipment functional technical indicators, fault root causes and fault phenomena.

[0172] Example 4

[0173] Based on Example 1, step S3, which involves designing a similarity matching algorithm, includes the following sub-steps:

[0174] S31, based on the analyzed equipment function knowledge structure tree, establish function sets, integrated sub-unit sets, and configuration module sets, and set:

[0175] The set of functions F = {f1, f2, f3, ..., f n1};

[0176] Integrated extension set I = {i1,i2,i3,…,i n2};

[0177] The configuration module set M = {m1, m2, m3, ..., m} n3};

[0178] Among them, f n1 For a specific function implemented by integrated aviation equipment, n1 is the number of functions, i n2 An integrated sub-unit for realizing a certain function in integrated aviation equipment, where n2 is the number of sub-units, and m n3 The configuration modules required to realize a certain function of integrated aviation equipment, where n3 is the number of modules;

[0179] S32, based on the analyzed equipment functional fault mapping, establish a set of functional technical indicators and set:

[0180] Technical indicator set T = {t1, t2, t3, ..., t n4};

[0181] Among them, t n4 n4 represents a specific functional technical indicator for integrated aviation equipment, where n4 is the number of functional technical indicators.

[0182] S33, for the target fault phenomenon description and a standard fault phenomenon description in the debugging fault knowledge base, the text values ​​are segmented using a Chinese word segmentation algorithm of natural language processing to obtain two fault phenomenon word sets, set as follows:

[0183] Target Fault Phenomenon Terminology

[0184] Standard Fault Phenomenon Terminology

[0185] in, The target fault phenomenon is described by word segmentation, where n5 is the number of words to be segmented. The description of a standard fault phenomenon is segmented into words, where n6 is the number of words to be segmented.

[0186] S34, Settings:

[0187] C1=F∩W T ct1 is the number of elements in set C1;

[0188] C2=I∩W T ct2 is the number of elements in set C2;

[0189] C3=M∩W T ct3 is the number of elements in set C3;

[0190] C4=T∩W T ct4 represents the number of elements in set C4;

[0191] C5 = W S ∩W T ct5 represents the number of elements in set C5;

[0192] S35, based on the different degrees of influence of integrated fault attributes, functional attributes, integrated sub-units, configuration modules, and technical indicators on fault diagnosis, weights are assigned to them as P1, P2, P3, and P4 respectively. The similarity of the target fault is then calculated as follows:

[0193]

[0194] S36, For the standard fault records in the debugging fault knowledge base, repeat steps S33 to S35 to obtain a set of target fault similarities. Where e i To test the number of standard fault records in the fault knowledge base, the standard fault record corresponding to the maximum value in the similarity array is the matching output result.

[0195] Example 5

[0196] Based on Example 1, in step S4, the fault knowledge base is improved. Specifically, for cases where the similarity matching algorithm fails to match the result or the standard fault knowledge matched cannot solve the target fault, the technical personnel solve the target fault, and at the same time, the fault knowledge data is recorded according to the fault attributes and fault elements.

[0197] Example 6

[0198] Based on Example 2, the product attributes are equipment component entities, including equipment functions, sub-units, and modules;

[0199] The environmental attributes refer to the environmental conditions when the fault occurs, including normal temperature, high temperature, low temperature, low pressure, and vibration.

[0200] The logical attributes represent the root causes and solutions for debugging failures. The root causes include component, software, and process factors, representing the causal relationship that leads to the failure phenomenon.

[0201] Example 7

[0202] Based on Example 3, the logical relationships between the fault phenomena include belonging relationships, causing relationships, and associating relationships;

[0203] The relationship described is that the fault phenomenon belongs to a certain product attribute of the equipment;

[0204] The aforementioned relationship is that a failure of a certain component of the equipment leads to a failure of a certain attribute of the product, or a failure of a certain attribute of the product leads to a failure of another product attribute, which exists in the equipment function implementation process.

[0205] The correlation is the relationship between the product failure phenomenon and the failure environment attributes of the debugging system.

[0206] Example 8

[0207] A fault diagnosis system based on debugging experience includes:

[0208] The preprocessing module is used for preprocessing test fault data;

[0209] The diagnostic knowledge model building module is used to build diagnostic knowledge models;

[0210] The similarity matching module is used to design similarity matching algorithms to match target fault phenomena with the fault experience knowledge base.

[0211] The Fault Knowledge Base Improvement Module is used to improve the fault knowledge base.

[0212] Example 9

[0213] Based on Example 8, the diagnostic knowledge model construction module includes a functional knowledge structure analysis module and a functional fault mapping analysis module;

[0214] The functional knowledge structure analysis module is used to sort out the set of equipment working functions, integrated sub-units, and configuration modules through the design principles of integrated aviation equipment, and form a standardized functional knowledge structure tree.

[0215] The functional fault mapping analysis module is used to establish the logical relationship between equipment functional technical indicators, fault root causes and fault phenomena based on existing commissioning and testing fault experience data.

[0216] Example 10

[0217] Based on Example 8, the similarity matching module includes:

[0218] The first settings module is used to establish a set of functions, a set of integrated sub-units, and a set of configuration modules based on the sorted equipment function knowledge structure tree. Settings include:

[0219] The set of functions F = {f1, f2, f3, ..., f n1};

[0220] Integrated extension set I = {i1,i2,i3,…,i n2};

[0221] The configuration module set M = {m1, m2, m3, ..., m} n3};

[0222] Among them, f n1 For a specific function implemented by integrated aviation equipment, n1 is the number of functions, i n2 An integrated sub-unit for realizing a certain function in integrated aviation equipment, where n2 is the number of sub-units, and m n3 The configuration modules required to realize a certain function of integrated aviation equipment, where n3 is the number of modules;

[0223] The second setting module is used to establish a set of functional technical indicators based on the analyzed equipment functional fault mapping. The settings include:

[0224] Technical indicator set T = {t1, t2, t3, ..., t n4};

[0225] Among them, t n4 n4 represents a specific functional technical indicator for integrated aviation equipment, where n4 is the number of functional technical indicators.

[0226] The third setting module is used to segment the text values ​​of the target fault phenomenon description and a standard fault phenomenon description from the debugging fault knowledge base using a Chinese word segmentation algorithm based on natural language processing, resulting in two fault phenomenon word sets. The settings are as follows:

[0227] Target Fault Phenomenon Terminology

[0228] Standard Fault Phenomenon Terminology

[0229] in, The target fault phenomenon is described by word segmentation, where n5 is the number of words to be segmented. The description of a standard fault phenomenon is segmented into words, where n6 is the number of words to be segmented.

[0230] The fourth settings module is used to configure:

[0231] C1=F∩W T ct1 is the number of elements in set C1;

[0232] C2=I∩W T ct2 is the number of elements in set C2;

[0233] C3=M∩W T ct3 is the number of elements in set C3;

[0234] C4=T∩W T ct4 represents the number of elements in set C4;

[0235] C5 = W S ∩W T ct5 represents the number of elements in set C5;

[0236] The target fault similarity calculation module is used to assign weights P1, P2, P3, and P4 to the comprehensive fault attributes, functional attributes, integrated sub-units, configuration modules, and technical indicators based on their varying degrees of influence on fault diagnosis. The target fault similarity is then calculated as follows:

[0237]

[0238] The maximum value lookup module is used to repeat the process from the third setting module to the target fault similarity calculation module for standard fault records in the debugging fault knowledge base, to obtain a set of target fault similarities. Where e i To test the number of standard fault records in the fault knowledge base, the standard fault record corresponding to the maximum value in the similarity array is the matching output result.

[0239] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0240] According to one aspect of the present invention, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations described above.

[0241] In another aspect, embodiments of the present invention also provide a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0242] All parts not covered in this invention are the same as or can be implemented using existing technologies.

[0243] The above technical solution is only one embodiment of the present invention. For those skilled in the art, based on the application methods and principles disclosed in the present invention, it is easy to make various types of improvements or modifications, and not limited to the methods described in the above specific embodiments of the present invention. Therefore, the methods described above are only preferred and are not restrictive.

[0244] In addition to the examples above, other embodiments may be obtained by those skilled in the art based on the above disclosure or by making modifications using knowledge or technology in related fields. The features of each embodiment may be interchanged or replaced. Modifications and changes made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A fault diagnosis design method based on debugging and testing experience, characterized in that, Includes the following steps: S1, Preprocessing of fault data during commissioning; S2, Construct a diagnostic knowledge model; S3, Design a similarity matching algorithm to match the target fault phenomenon with the fault experience knowledge base; the design of the similarity matching algorithm includes the following sub-steps: S31, based on the analyzed equipment function knowledge structure tree, establish function sets, integrated sub-unit sets, and configuration module sets, and set: The function set F = {f1, f2, f3, ..., f n1 }; Integrated extension set I={i1,i2,i3,…,i n2 }; The configuration module set M = {m1, m2, m3, ..., m} n3 }; Among them, f n1 For a specific function implemented by integrated aviation equipment, n1 is the number of functions, i n2 An integrated sub-unit for realizing a certain function in integrated aviation equipment, where n2 is the number of sub-units, and m n3 The configuration modules required to realize a certain function of integrated aviation equipment, where n3 is the number of modules; S32, based on the analyzed equipment functional fault mapping, establish a set of functional technical indicators and set: Technical indicator set T={t1,t2,t3,…,t n4 }; Among them, t n4 n4 represents a specific functional technical indicator for integrated aviation equipment, where n4 is the number of functional technical indicators. S33, for the target fault phenomenon description and a standard fault phenomenon description in the debugging fault knowledge base, the text values ​​are segmented using a Chinese word segmentation algorithm of natural language processing to obtain two fault phenomenon word sets, set as follows: Target Fault Phenomenon Terminology W T ={ , , ,…, }; Standard Fault Phenomenon Terminology W S ={ , , ,…, }; in, The target fault phenomenon is described by word segmentation, where n5 is the number of words to be segmented. The description of a standard fault phenomenon is segmented into words, where n6 is the number of words to be segmented. S34, Settings: C1=F∩W T ct1 is the number of elements in set C1; C2=I∩W T ct2 is the number of elements in set C2; C3=M∩W T ct3 is the number of elements in set C3; C4=T∩W T ct4 represents the number of elements in set C4; C5=W S ∩W T ct5 represents the number of elements in set C5; S35, based on the different degrees of influence of integrated fault attributes, functional attributes, integrated sub-units, configuration modules, and technical indicators on fault diagnosis, weights are assigned to them as P1, P2, P3, and P4 respectively. The similarity of the target fault is then calculated as follows: S36, For the standard fault records in the debugging fault knowledge base, repeat steps S33 to S35 to obtain a set of target fault similarities. ,in To determine the number of standard fault records in the fault knowledge base, the standard fault record corresponding to the maximum value in the similarity array is the matching output result. S4, with an improved fault knowledge base.

2. The fault diagnosis design method based on debugging and testing experience knowledge according to claim 1, characterized in that, In step S1, the preprocessing of the debugging fault data specifically includes: debugging fault attribute analysis, debugging fault element extraction, and debugging fault data transformation. The aforementioned fault attribute analysis, through the analysis of the debugging process of integrated aviation equipment, and based on empirical fault data, classifies the product attributes, environmental attributes, and logical attributes of equipment debugging faults, forming attribute classes. The extraction of debugging and testing fault elements involves analyzing existing experience fault data of integrated aviation equipment and combining it with the unique attributes of debugging and testing faults to form a debugging and testing fault element table. The debugging and testing fault data transformation involves transforming existing debugging and testing fault data according to the debugging and testing fault element table to form a standardized debugging and testing fault experience database.

3. The fault diagnosis design method based on debugging and testing experience knowledge according to claim 1, characterized in that, In step S2, the construction of the diagnostic knowledge model specifically includes: functional knowledge structure analysis and functional fault mapping analysis; The functional knowledge structure analysis, through the design principles of integrated aviation equipment, sorts out the equipment's functional sets, integrated sub-units, and configuration modules to form a standardized functional knowledge structure tree. The functional fault mapping analysis is based on existing commissioning and testing fault experience data, and establishes the logical relationship between equipment functional technical indicators, fault root causes and fault phenomena.

4. The fault diagnosis design method based on debugging and testing experience knowledge according to claim 1, characterized in that, In step S4, the fault knowledge base is improved. Specifically, for cases where the similarity matching algorithm fails to find a match or the standard fault knowledge found cannot resolve the target fault, the technical personnel resolve the target fault, and at the same time, fault knowledge data is recorded according to the fault attributes and fault elements.

5. The fault diagnosis design method based on debugging and testing experience knowledge according to claim 2, characterized in that, The product attributes are the equipment components, including equipment functions, sub-units, and modules; The environmental attributes refer to the environmental conditions when the fault occurs, including normal temperature, high temperature, low temperature, low pressure, and vibration. The logical attributes represent the root causes and solutions for debugging failures. The root causes include component, software, and process factors, representing the causal relationship that leads to the failure phenomenon.

6. The fault diagnosis design method based on debugging and testing experience knowledge according to claim 3, characterized in that, The logical relationships between the fault phenomena include belonging relationships, causing relationships, and associative relationships; The relationship described is that the fault phenomenon belongs to a certain product attribute of the equipment; The aforementioned relationship is that a failure of a certain component of the equipment leads to a failure of a certain attribute of the product, or a failure of a certain attribute of the product leads to a failure of another product attribute, which exists in the equipment function implementation process. The correlation is the relationship between the product failure phenomenon and the failure environment attributes of the debugging system.

7. A fault diagnosis system based on debugging and testing experience, characterized in that, include: The preprocessing module is used for preprocessing test fault data; The diagnostic knowledge model building module is used to build diagnostic knowledge models; The similarity matching module is used to design similarity matching algorithms to match target fault phenomena with the fault experience knowledge base. The similarity matching module includes: The first settings module is used to establish a set of functions, a set of integrated sub-units, and a set of configuration modules based on the sorted equipment function knowledge structure tree. Settings include: The function set F = {f1, f2, f3, ..., f n1 }; Integrated extension set I={i1,i2,i3,…,i n2 }; The configuration module set M = {m1, m2, m3, ..., m} n3 }; Among them, f n1 For a specific function implemented by integrated aviation equipment, n1 is the number of functions, i n2 An integrated sub-unit for realizing a certain function in integrated aviation equipment, where n2 is the number of sub-units, and m n3 The configuration modules required to realize a certain function of integrated aviation equipment, where n3 is the number of modules; The second setting module is used to establish a set of functional technical indicators based on the analyzed equipment functional fault mapping. The settings include: Technical indicator set T={t1,t2,t3,…,t n4 }; Among them, t n4 n4 represents a specific functional technical indicator for integrated aviation equipment, where n4 is the number of functional technical indicators. The third setting module is used to segment the text values ​​of the target fault phenomenon description and a standard fault phenomenon description from the debugging fault knowledge base using a Chinese word segmentation algorithm based on natural language processing, resulting in two fault phenomenon word sets. The settings are as follows: Target Fault Phenomenon Terminology W T ={ , , ,…, }; Standard Fault Phenomenon Terminology W S ={ , , ,…, }; in, The target fault phenomenon is described by word segmentation, where n5 is the number of words to be segmented. The description of a standard fault phenomenon is segmented into words, where n6 is the number of words to be segmented. The fourth settings module is used to configure: C1=F∩W T ct1 is the number of elements in set C1; C2=I∩W T ct2 is the number of elements in set C2; C3=M∩W T ct3 is the number of elements in set C3; C4=T∩W T ct4 represents the number of elements in set C4; C5=W S ∩W T ct5 represents the number of elements in set C5; The target fault similarity calculation module is used to assign weights P1, P2, P3, and P4 to the comprehensive fault attributes, functional attributes, integrated sub-units, configuration modules, and technical indicators based on their varying degrees of influence on fault diagnosis. The target fault similarity is then calculated as follows: The maximum value lookup module is used to repeat the process from the third setting module to the target fault similarity calculation module for standard fault records in the debugging fault knowledge base, to obtain a set of target fault similarities. ,in To determine the number of standard fault records in the fault knowledge base, the standard fault record corresponding to the maximum value in the similarity array is the matching output result. The Fault Knowledge Base Improvement Module is used to improve the fault knowledge base.

8. The fault diagnosis system based on debugging and testing experience knowledge according to claim 7, characterized in that, The diagnostic knowledge model construction module includes a functional knowledge structure analysis module and a functional fault mapping analysis module; The functional knowledge structure analysis module is used to sort out the set of equipment working functions, integrated sub-units, and configuration modules through the design principles of integrated aviation equipment, and form a standardized functional knowledge structure tree. The functional fault mapping analysis module is used to establish the logical relationship between equipment functional technical indicators, fault root causes and fault phenomena based on existing commissioning and testing fault experience data.

Images